INDEX

Explanations

words related to fire, combustion, and sparking

oai_token-act-pair · gpt-3.5-turbo

words related to ignition or starting fires

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iago

-0.81

umbo

-0.78

usterity

-0.77

thodox

-0.74

roman

-0.72

tarian

-0.71

ull

-0.71

alian

-0.70

romy

-0.67

alloc

-0.66

POSITIVE LOGITS

 combust

1.13

ign

1.12

 ignite

1.04

 ignition

0.91

 extingu

0.86

 ashes

0.86

 ignited

0.81

 fuse

0.80

encing

0.77

 FIRE

0.76

Activations Density 0.016%

words related to fire, combustion, and sparking

words related to ignition or starting fires

No Comments

No Known Activations